Unknown SAR Target Identification Method Based on Feature Extraction Network and KLD–RPA Joint Discrimination
| العنوان: | Unknown SAR Target Identification Method Based on Feature Extraction Network and KLD–RPA Joint Discrimination |
|---|---|
| المؤلفون: | Haiyang Wang, Jinping Sun, Zhiqiang Zeng, Congan Xu |
| المصدر: | Remote Sensing Volume 13 Issue 15 Pages: 2901 Remote Sensing, Vol 13, Iss 2901, p 2901 (2021) |
| بيانات النشر: | MDPI AG, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Synthetic aperture radar, Kullback–Leibler divergence, Computer science, Science, Feature vector, Feature extraction, 0211 other engineering and technologies, automatic target recognition, 02 engineering and technology, Automatic target recognition, 0203 mechanical engineering, 021101 geological & geomatics engineering, 020301 aerospace & aeronautics, business.industry, Deep learning, Dimensionality reduction, fungi, deep learning, Pattern recognition, relative position angle, Identification (information), General Earth and Planetary Sciences, Artificial intelligence, business, synthetic aperture radar |
| الوصف: | Recently, deep learning (DL) has been successfully applied in automatic target recognition (ATR) tasks of synthetic aperture radar (SAR) images. However, limited by the lack of SAR image target datasets and the high cost of labeling, these existing DL based approaches can only accurately recognize the target in the training dataset. Therefore, high precision identification of unknown SAR targets in practical applications is one of the important capabilities that the SAR–ATR system should equip. To this end, we propose a novel DL based identification method for unknown SAR targets with joint discrimination. First of all, the feature extraction network (FEN) trained on a limited dataset is used to extract the SAR target features, and then the unknown targets are roughly identified from the known targets by computing the Kullback–Leibler divergence (KLD) of the target feature vectors. For the targets that cannot be distinguished by KLD, their feature vectors perform t-distributed stochastic neighbor embedding (t-SNE) dimensionality reduction processing to calculate the relative position angle (RPA). Finally, the known and unknown targets are finely identified based on RPA. Experimental results conducted on the MSTAR dataset demonstrate that the proposed method can achieve higher identification accuracy of unknown SAR targets than existing methods while maintaining high recognition accuracy of known targets. |
| وصف الملف: | application/pdf |
| تدمد: | 2072-4292 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ff69e02a1e7cb213b06d89e1b15f976Test https://doi.org/10.3390/rs13152901Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....7ff69e02a1e7cb213b06d89e1b15f976 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 20724292 |
|---|